Merge PR #455: fix UTF-8 encoding and ensure_ascii for non-ASCII support

nanobot/agent/loop.py

@@ -206,7 +206,7 @@ class AgentLoop:
                         "type": "function",
                         "function": {
                             "name": tc.name,
-                            "arguments": json.dumps(tc.arguments)
+                            "arguments": json.dumps(tc.arguments, ensure_ascii=False)
                         }
                     }
                     for tc in response.tool_calls

nanobot/agent/subagent.py

@@ -146,7 +146,7 @@ class SubagentManager:
                             "type": "function",
                             "function": {
                                 "name": tc.name,
-                                "arguments": json.dumps(tc.arguments),
+                                "arguments": json.dumps(tc.arguments, ensure_ascii=False),
                             },
                         }
                         for tc in response.tool_calls
@@ -159,7 +159,7 @@ class SubagentManager:
                     
                     # Execute tools
                     for tool_call in response.tool_calls:
-                        args_str = json.dumps(tool_call.arguments)
+                        args_str = json.dumps(tool_call.arguments, ensure_ascii=False)
                         logger.debug("Subagent [{}] executing: {} with arguments: {}", task_id, tool_call.name, args_str)
                         result = await tools.execute(tool_call.name, tool_call.arguments)
                         messages.append({

nanobot/agent/tools/web.py

@@ -116,7 +116,7 @@ class WebFetchTool(Tool):
         # Validate URL before fetching
         is_valid, error_msg = _validate_url(url)
         if not is_valid:
-            return json.dumps({"error": f"URL validation failed: {error_msg}", "url": url})
+            return json.dumps({"error": f"URL validation failed: {error_msg}", "url": url}, ensure_ascii=False)
 
         try:
             async with httpx.AsyncClient(
@@ -131,7 +131,7 @@ class WebFetchTool(Tool):
             
             # JSON
             if "application/json" in ctype:
-                text, extractor = json.dumps(r.json(), indent=2), "json"
+                text, extractor = json.dumps(r.json(), indent=2, ensure_ascii=False), "json"
             # HTML
             elif "text/html" in ctype or r.text[:256].lower().startswith(("<!doctype", "<html")):
                 doc = Document(r.text)
@@ -146,9 +146,9 @@ class WebFetchTool(Tool):
                 text = text[:max_chars]
             
             return json.dumps({"url": url, "finalUrl": str(r.url), "status": r.status_code,
-                              "extractor": extractor, "truncated": truncated, "length": len(text), "text": text})
+                              "extractor": extractor, "truncated": truncated, "length": len(text), "text": text}, ensure_ascii=False)
         except Exception as e:
-            return json.dumps({"error": str(e), "url": url})
+            return json.dumps({"error": str(e), "url": url}, ensure_ascii=False)
     
     def _to_markdown(self, html: str) -> str:
         """Convert HTML to markdown."""

nanobot/channels/dingtalk.py

@@ -208,7 +208,7 @@ class DingTalkChannel(BaseChannel):
             "msgParam": json.dumps({
                 "text": msg.content,
                 "title": "Nanobot Reply",
-            }),
+            }, ensure_ascii=False),
         }
 
         if not self._http:

nanobot/channels/feishu.py

@@ -390,7 +390,7 @@ class FeishuChannel(BaseChannel):
                     if key:
                         await loop.run_in_executor(
                             None, self._send_message_sync,
-                            receive_id_type, msg.chat_id, "image", json.dumps({"image_key": key}),
+                            receive_id_type, msg.chat_id, "image", json.dumps({"image_key": key}, ensure_ascii=False),
                         )
                 else:
                     key = await loop.run_in_executor(None, self._upload_file_sync, file_path)
@@ -398,7 +398,7 @@ class FeishuChannel(BaseChannel):
                         media_type = "audio" if ext in self._AUDIO_EXTS else "file"
                         await loop.run_in_executor(
                             None, self._send_message_sync,
-                            receive_id_type, msg.chat_id, media_type, json.dumps({"file_key": key}),
+                            receive_id_type, msg.chat_id, media_type, json.dumps({"file_key": key}, ensure_ascii=False),
                         )
 
             if msg.content and msg.content.strip():

nanobot/channels/whatsapp.py

@@ -87,7 +87,7 @@ class WhatsAppChannel(BaseChannel):
                 "to": msg.chat_id,
                 "text": msg.content
             }
-            await self._ws.send(json.dumps(payload))
+            await self._ws.send(json.dumps(payload, ensure_ascii=False))
         except Exception as e:
             logger.error("Error sending WhatsApp message: {}", e)
     

nanobot/cli/commands.py

@@ -243,7 +243,7 @@ Information about the user goes here.
     for filename, content in templates.items():
         file_path = workspace / filename
         if not file_path.exists():
-            file_path.write_text(content)
+            file_path.write_text(content, encoding="utf-8")
             console.print(f"  [dim]Created {filename}[/dim]")
     
     # Create memory directory and MEMORY.md
@@ -266,12 +266,12 @@ This file stores important information that should persist across sessions.
 ## Important Notes
 
 (Things to remember)
-""")
+""", encoding="utf-8")
         console.print("  [dim]Created memory/MEMORY.md[/dim]")
     
     history_file = memory_dir / "HISTORY.md"
     if not history_file.exists():
-        history_file.write_text("")
+        history_file.write_text("", encoding="utf-8")
         console.print("  [dim]Created memory/HISTORY.md[/dim]")
 
     # Create skills directory for custom user skills

nanobot/config/loader.py

@@ -31,7 +31,7 @@ def load_config(config_path: Path | None = None) -> Config:
 
     if path.exists():
         try:
-            with open(path) as f:
+            with open(path, encoding="utf-8") as f:
                 data = json.load(f)
             data = _migrate_config(data)
             return Config.model_validate(data)
@@ -55,8 +55,8 @@ def save_config(config: Config, config_path: Path | None = None) -> None:
 
     data = config.model_dump(by_alias=True)
 
-    with open(path, "w") as f:
+    with open(path, "w", encoding="utf-8") as f:
-        json.dump(data, f, indent=2)
+        json.dump(data, f, indent=2, ensure_ascii=False)
 
 
 def _migrate_config(data: dict) -> dict:

nanobot/cron/service.py

@@ -66,7 +66,7 @@ class CronService:
         
         if self.store_path.exists():
             try:
-                data = json.loads(self.store_path.read_text())
+                data = json.loads(self.store_path.read_text(encoding="utf-8"))
                 jobs = []
                 for j in data.get("jobs", []):
                     jobs.append(CronJob(
@@ -148,7 +148,7 @@ class CronService:
             ]
         }
         
-        self.store_path.write_text(json.dumps(data, indent=2))
+        self.store_path.write_text(json.dumps(data, indent=2, ensure_ascii=False), encoding="utf-8")
     
     async def start(self) -> None:
         """Start the cron service."""

nanobot/heartbeat/service.py

@@ -65,7 +65,7 @@ class HeartbeatService:
         """Read HEARTBEAT.md content."""
         if self.heartbeat_file.exists():
             try:
-                return self.heartbeat_file.read_text()
+                return self.heartbeat_file.read_text(encoding="utf-8")
             except Exception:
                 return None
         return None

nanobot/providers/openai_codex_provider.py

@@ -176,7 +176,7 @@ def _convert_messages(messages: list[dict[str, Any]]) -> tuple[str, list[dict[st
 
         if role == "tool":
             call_id, _ = _split_tool_call_id(msg.get("tool_call_id"))
-            output_text = content if isinstance(content, str) else json.dumps(content)
+            output_text = content if isinstance(content, str) else json.dumps(content, ensure_ascii=False)
             input_items.append(
                 {
                     "type": "function_call_output",

nanobot/session/manager.py

@@ -121,7 +121,7 @@ class SessionManager:
             created_at = None
             last_consolidated = 0
 
-            with open(path) as f:
+            with open(path, encoding="utf-8") as f:
                 for line in f:
                     line = line.strip()
                     if not line:
@@ -151,7 +151,7 @@ class SessionManager:
         """Save a session to disk."""
         path = self._get_session_path(session.key)
 
-        with open(path, "w") as f:
+        with open(path, "w", encoding="utf-8") as f:
             metadata_line = {
                 "_type": "metadata",
                 "created_at": session.created_at.isoformat(),
@@ -159,9 +159,9 @@ class SessionManager:
                 "metadata": session.metadata,
                 "last_consolidated": session.last_consolidated
             }
-            f.write(json.dumps(metadata_line) + "\n")
+            f.write(json.dumps(metadata_line, ensure_ascii=False) + "\n")
             for msg in session.messages:
-                f.write(json.dumps(msg) + "\n")
+                f.write(json.dumps(msg, ensure_ascii=False) + "\n")
 
         self._cache[session.key] = session
     
@@ -181,7 +181,7 @@ class SessionManager:
         for path in self.sessions_dir.glob("*.jsonl"):
             try:
                 # Read just the metadata line
-                with open(path) as f:
+                with open(path, encoding="utf-8") as f:
                     first_line = f.readline().strip()
                     if first_line:
                         data = json.loads(first_line)